Fetching from the wire…
01
02
03
04
05
06
07
08
Markets2026-07-29 · source-backed
Prelint checks every PR against structured product specs compiled into a product knowledge graph, rather than against lint rules. Its AI Code Pulse research, graded across 56,706 PRs from 331 open-source repos, found Claude tooling in 81% of repos, Cursor in 40%, Copilot in 22%, CodeRabbit in 9%, and 46% of repos configuring multiple AI vendors. The most useful number for builders: reviews run with documentation hit 80.8% precision, surfacing 979 additional real issues while preventing 232 false alarms versus blind review. The dataset carries a February 2026 update stamp; the launch is what's new.
Each link below shares sources, entities, or timing with this story.
wanshuiyin/HERO-Anti-OverDefense went from creation to 68 stars in a single day. HERO is Hashing, Edge cases, Rubrics, Overbuild, and the claim is that agent over-engineering isn't diffuse but falls into four recognizable shapes suppressible with a portable prompt contract acr...
We've been operating on faith here. Everyone tells you to write an AGENTS.md or CLAUDE.md, you write one, and you assume it helps because it feels like it should. Now there's data, and it's more interesting than "yes, write the file." A study of 15,549 agentic pull requests ac...
Researchers analyzed 61,837 GitHub Actions runs from 2,355 repos triggered by PRs from Claude, Devin, Cursor, Copilot, and Codex. Substantial differences in pass rates across bots. This is the first empirical data on how AI-generated code actually performs under real CI/CD con...
A free-alpha macOS app plus GitHub extension and MCP server that answers "why" questions from a repo's own pull requests and issues, shows the evidence, and says nobody wrote this down when nobody did (Icarus). The insight underneath: merged PRs leave commits but refused ones...
GitHub expanded Copilot's Rubber Duck mode with something that caught my attention: cross-family review. Claude now critiques GPT-authored sessions. GPT-5.5 reviews Claude sessions. Two different model families, trained on different data with different failure modes, checking...
Across the AIDev dataset, nearly half of fixes from Copilot, Devin, Cursor, and Claude are rejected, sorted into incorrect implementation, CI failures, inability to execute the fix, and low priority (arXiv). The fix the authors push: better model guidance on implementation app...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.